{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RABTI6K65ZHFSBY7UJDWWIZZVO","short_pith_number":"pith:RABTI6K6","schema_version":"1.0","canonical_sha256":"880334795eee4e59071fa2476b2339aba0f2028e0cdb9a77c02ae2fd7aa2a685","source":{"kind":"arxiv","id":"2404.09911","version":2},"attestation_state":"computed","paper":{"title":"ChatShop: Interactive Information Seeking with Language Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bhuwan Dhingra, Sam Wiseman, Sanxing Chen","submitted_at":"2024-04-15T16:35:41Z","abstract_excerpt":"The desire and ability to seek new information strategically are fundamental to human learning but often overlooked in current language agent evaluation. We analyze a popular web shopping task designed to test language agents' ability to perform strategic exploration and discover that it can be reformulated and solved as a single-turn retrieval task without the need for interactive information seeking. This finding encourages us to rethink realistic constraints on information access that would necessitate strategic information seeking. We then redesign the task to introduce a notion of task am"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2404.09911","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-15T16:35:41Z","cross_cats_sorted":[],"title_canon_sha256":"479b662445ba2f1c68b787ef58b95fc7157c927d4bb6a1ff2820496109ce0d76","abstract_canon_sha256":"47df928c5c60227d5c7dbbb995f420acd4614c3a859b30488f3f6c3d8c80c326"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:39.475632Z","signature_b64":"9n4tQ9N3vgSCxQti6Haz36G6IuUde+mSITGOnUmWOyOpazIYrBRg/LVViKbzbMyNLtvfWfym9ARIzzb69v6MCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"880334795eee4e59071fa2476b2339aba0f2028e0cdb9a77c02ae2fd7aa2a685","last_reissued_at":"2026-07-05T08:32:39.475133Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:39.475133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChatShop: Interactive Information Seeking with Language Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bhuwan Dhingra, Sam Wiseman, Sanxing Chen","submitted_at":"2024-04-15T16:35:41Z","abstract_excerpt":"The desire and ability to seek new information strategically are fundamental to human learning but often overlooked in current language agent evaluation. We analyze a popular web shopping task designed to test language agents' ability to perform strategic exploration and discover that it can be reformulated and solved as a single-turn retrieval task without the need for interactive information seeking. This finding encourages us to rethink realistic constraints on information access that would necessitate strategic information seeking. We then redesign the task to introduce a notion of task am"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09911","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.09911/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2404.09911","created_at":"2026-07-05T08:32:39.475188+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.09911v2","created_at":"2026-07-05T08:32:39.475188+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09911","created_at":"2026-07-05T08:32:39.475188+00:00"},{"alias_kind":"pith_short_12","alias_value":"RABTI6K65ZHF","created_at":"2026-07-05T08:32:39.475188+00:00"},{"alias_kind":"pith_short_16","alias_value":"RABTI6K65ZHFSBY7","created_at":"2026-07-05T08:32:39.475188+00:00"},{"alias_kind":"pith_short_8","alias_value":"RABTI6K6","created_at":"2026-07-05T08:32:39.475188+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06118","citing_title":"WebRetriever: A Large-Scale Comprehensive Benchmark for Efficient Web Agent Evaluation","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19219","citing_title":"SimGym: A Framework for A/B Test Simulation in E-Commerce with Traffic-Grounded VLM Agents","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2508.15832","citing_title":"A Functionality-Grounded Benchmark for Evaluating Web Agents in E-commerce Domains","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2406.12045","citing_title":"$\\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RABTI6K65ZHFSBY7UJDWWIZZVO","json":"https://pith.science/pith/RABTI6K65ZHFSBY7UJDWWIZZVO.json","graph_json":"https://pith.science/api/pith-number/RABTI6K65ZHFSBY7UJDWWIZZVO/graph.json","events_json":"https://pith.science/api/pith-number/RABTI6K65ZHFSBY7UJDWWIZZVO/events.json","paper":"https://pith.science/paper/RABTI6K6"},"agent_actions":{"view_html":"https://pith.science/pith/RABTI6K65ZHFSBY7UJDWWIZZVO","download_json":"https://pith.science/pith/RABTI6K65ZHFSBY7UJDWWIZZVO.json","view_paper":"https://pith.science/paper/RABTI6K6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.09911&json=true","fetch_graph":"https://pith.science/api/pith-number/RABTI6K65ZHFSBY7UJDWWIZZVO/graph.json","fetch_events":"https://pith.science/api/pith-number/RABTI6K65ZHFSBY7UJDWWIZZVO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RABTI6K65ZHFSBY7UJDWWIZZVO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RABTI6K65ZHFSBY7UJDWWIZZVO/action/storage_attestation","attest_author":"https://pith.science/pith/RABTI6K65ZHFSBY7UJDWWIZZVO/action/author_attestation","sign_citation":"https://pith.science/pith/RABTI6K65ZHFSBY7UJDWWIZZVO/action/citation_signature","submit_replication":"https://pith.science/pith/RABTI6K65ZHFSBY7UJDWWIZZVO/action/replication_record"}},"created_at":"2026-07-05T08:32:39.475188+00:00","updated_at":"2026-07-05T08:32:39.475188+00:00"}